http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Improving the Image Classification of PET Bottle Using Transfer Learning Approach
Subhajit Chatterjee,Yung-Cheol Byun 한국정보기술학회 2021 Proceedings of KIIT Conference Vol.2021 No.11
The main objective of this study is to classify the plastic bottle images correctly that will have great value in the waste management industry. It is a fact that convolutional neural networks have revolutionized image classification. But most of these algorithms require large amounts of labeled data for training. When considering image classification of plastic bottle images, datasets need to be large and balanced. To overcome this issue, we applied the importance of data augmentation for balancing the dataset. This experiment aims to different data augmentation methods and transfer learning to improve the classification result. To evaluate the model, the model obtained an accuracy of 98.97%. We wrap up our research with a detailed examination of each of these strategies and a comparison of their results
Towards Intelligent Road Situation Detection with Deep Learning Approaches
Subhajit Chatterjee,Yung-Cheol Byun 한국정보기술학회 2024 Proceedings of The International Workshop on Futur Vol.2024 No.4
The growing importance of video situation classification lies in its ability to understand and classify road situations. This field has seen significant progress in recent years, fueled by advancements in deep learning models. However, a major challenge remains, existing systems often require extensive video data for training. While this approach can achieve excellent results, it often necessitates pre-training these models on massive datasets a process impractical for applications with limited video data. To address this data-efficiency bottleneck, we employed Video-masked Autoencoders (VideoMAE) as a pre-training technique for road video situation classification. VideoMAE utilizes a self-supervised learning approach, enabling it to learn meaningful representations from unlabeled video data. We evaluate multiple iterations of our VideoMAE model on a road video dataset. Our results demonstrate that VideoMAE achieves impressive performance even with a very limited dataset. This data efficiency makes Video-MAE a compelling solution for real-time road situation classification tasks in resource-constrained environments.
Mahuya Pakhira,Subhajit Ghosh,Surajit Ghosh,Dhruba P. Chatterjee,Arun K. Nandi 한국공업화학회 2022 Journal of Industrial and Engineering Chemistry Vol.112 No.-
Biocidal and anti-fouling properties in the same polymeric membranes are important in biomedical fieldfor their capability to protect serious infection and filtration of biological molecules. For this purpose wereport random graft copolymer of poly(vinylidene fluoride) (PVDF-graft-poly(tBAEMA-ran-OEGMA,PVBO) membranes showing both antifouling and antibacterial activity. The PVBO copolymer is synthesisedusing ATRP technique and the polymer membranes are produced by breath figure (PVBO-1) andphase inversion (PVBO-2) techniques. The former shows well-developed hexagonal pores (diameter15 ± 3.5 nm), and good hydrophilicity (contact angle 41.3). PVBO-1 membrane exhibits good antifoulingproperty for both lysozyme and BSA solutions. Antimicrobial activity measured from agar diffusionmethod indicates that PVBO-1 shows a large zone of inhibition in case of gram-negative E coli andgram-positive S. aureus bacteria, whereas PVBO-2 and its HCl treated state (PVBO-3) membranes exhibitonly a moderate zone of inhibition. The MBC and MIC values indicate that the synthesized membranesare bactericidal in nature and not bacteriostatic. Live and dead cell assay indicates that PVBO-1 can significantlyinhibit growth of bacteria even at high bacteria concentration confirming high antimicrobialactivity. MTT assay suggests PVBO-1 is non-cytotoxic to mammalian cells and co-culturing activity resultsuggests high cellular selectivity of PVBO-1.
Non-destructive Characterization of MSW-contaminated Surface Soils by EDXRF and low-Z Particle EPMA
Shila Maskey,Chul-Un Ro,Dhrubajyoti Gupta,Jyotsnamayee Chatterjee,Rita Ghosh,Ajoy Kumar Mitra,Subinit Roy,Manoranjan Sarkar,Subhajit Chowdhury,Asit Bhowmik,Ujjal Mukhopadhyay 한국대기환경학회 2010 한국대기환경학회 학술대회논문집 Vol.2010 No.5월